Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prepositions and related phrases indicating relationships or connections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    by names or initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hib
    -0.35
    -
    -0.33
     tas
    -0.32
    UIAlert
    -0.32
     critical
    -0.32
     party
    -0.30
     مفت
    -0.30
    <eos>
    -0.30
     ver
    -0.30
    FR
    -0.29
    POSITIVE LOGITS
    ✨:
    0.98
    fjspx
    0.93
     Италијани
    0.90
    [@BOS@]
    0.87
    <unused43>
    0.87
    <unused41>
    0.87
    <unused47>
    0.87
    <unused28>
    0.87
    <unused8>
    0.87
    <unused14>
    0.87
    Act Density 0.007%

    No Known Activations